多尺度非局部注意力网络的小目标检测算法

doi:10.3778/j.issn.1673-9418.1911024

摘要/Abstract

摘要：

现有的小目标检测方法通常采用多尺度特征图或利用多尺度融合特征进行检测，这些方法主要利用了特征图的空间信息而忽略了通道间的相互依赖关系。提出一种新的小目标检测网络，该网络在浅层利用非局部通道注意力模块整合特征的全局空间信息，进而对通道间的信息进行校准。从空间域及通道域获取特征的远距离依赖关系，增强浅层特征中小目标的上下文语义信息。同时，通过密集连接结构增强深层部分的特征提取能力，获取丰富的目标信息，提高目标检测任务的准确率和实时性。实验结果表明，该算法在PASCAL VOC、MS COCO数据集中得到了较好的检测结果，并且在保证检测速度的前提下，能有效提高小目标的检测准确率。

关键词: 目标检测, 卷积神经网络（CNN）, 非局部注意力, 密集连接

Abstract:

Existing small objects detection methods usually detect small objects by multi-scale feature maps or multi-scale fusion features. However, these methods mainly utilize the spatial information of the feature maps but ignore the interdependencies between channels. This paper proposes a novel small objects detection network, the network uses the non-local channel attention module to integrate the global spatial information of the features in the shallow layer, and then calibrates the information between channels. And from the spatial domain and the channel domain, it obtains the long-distance dependence of features and enhances the contextual semantic information of small targets in the shallow features. In addition, the network enhances the feature extraction capability of the deep features through dense connection structure, obtains rich target information, and improves the accuracy and real-time of the object detection task. The experimental results show that the algorithm has good detection results on PASCAL VOC and MS COCO datasets, and it can effectively improve the detection accuracy of small objects under the premise of ensuring the detection speed.

Key words: object detection, convolutional neural network (CNN), non-local attention, dense connection

梁延禹，李金宝. 多尺度非局部注意力网络的小目标检测算法[J]. 计算机科学与探索, 2020, 14(10): 1744-1753.

LIANG Yanyu, LI Jinbao. Small Objects Detection Method Based on Multi-scale Non-local Attention Network[J]. Journal of Frontiers of Computer Science and Technology, 2020, 14(10): 1744-1753.

参考文献

[1] Ren S Q, He K M, Girshick R, et al. Faster R-CNN: towards real-time object detection with region proposal networks[C]//Proceedings of the 28th Annual Conference on Neural Information Processing Systems, Montreal, Dec 7-12, 2015. Red Hook: Curran Associates, 2015: 91-99.
[2] Dai J F, Li Y, He K M, et al. R-FCN: object detection via region-based fully convolutional networks[C]//Proceedings of the 29th Annual Conference on Neural Information Processing Systems, Barcelona, Dec 5-10, 2016. Red Hook: Curran Asso-ciates, 2016: 379-387.
[3] Redmon J, Farhadi A. YOLO9000: better, faster, stronger[C]//Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, Jul 21-26, 2017. Piscataway: IEEE, 2017: 6517-6525.
[4] Chen X Z, Kundu K, Zhu Y K, et al. 3D object proposals for accurate object class detection[C]//Proceedings of the 28th Annual Conference on Neural Information Processing Systems, Montreal, Dec 7-12, 2015. Red Hook: Curran Associates, 2015: 424-432.
[5] Liu W, Anguelov D, Erhan D, et al. SSD: single shot multibox detector[C]//LNCS 9905: Proceedings of the 14th European Conference on Computer Vision, Amsterdam, Oct 11-14, 2016. Berlin, Heidelberg: Springer, 2016: 21-37.
[6] Zhu C C, He Y H, Savvides M. Feature selective anchor-free module for single-shot object detection[C]//Proceedings of the 2019 IEEE Conference on Computer Vision and Pattern Recognition, Long Beach, Jun 16-20, 2019. Piscataway: IEEE, 2019: 840-849.
[7] Li J Q, Liang X D, Wei Y C. Perceptual generative adversarial networks for small object detection[C]//Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, Jul 21-26, 2017. Piscataway: IEEE, 2017: 1951-1959.
[8] Everingham M, Gool L, Williams C, et al. The pascal visual object classes (voc) challenge[J]. International Journal of Computer Vision, 2010, 88(2): 303-338.
[9] Lin T Y, Maire M, Belongie S, et al. Microsoft COCO: common objects in context[C]//LNCS 8693: Proceedings of the 2014 European Conference on Computer Vision, Zurich, Sep 6-12, 2014. Berlin, Heidelberg: Springer, 2014: 740-755.
[10] Dalal N, Triggs B. Histograms of oriented gradients for human detection[C]//Proceedings of the 2005 IEEE Conference on Computer Vision and Pattern Recognition, San Diego, Jun 20-26, 2005. Piscataway: IEEE, 2005: 886-893.
[11] Shen Z Q, Liu Z, Li J G, et al. DSOD: learning deeply supervised object detectors from scratch[C]//Proceedings of the 2017 IEEE International Conference on Computer Vision, Venice, Oct 22-29, 2017. Piscataway: IEEE, 2017: 1937-1945.
[12] Huang G, Liu Z, Maaten L, et al. Densely connected convolutional networks[C]//Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, Jul 21-26, 2017. Piscataway: IEEE, 2017: 2261-2269.
[13] Cai Z W, Fan Q F, Feris R, et al. A unified multi-scale deep convolutional neural network for fast object detection[C]//LNCS 9908: Proceedings of the 2016 European Conference on Computer Vision, Amsterdam, Oct 11-14, 2016. Berlin, Heidelberg: Springer, 2016: 354-370.
[14] Liu S T, Huang D, Wang Y H. Receptive field block net for accurate and fast object detection[C]//LNCS 11215: Proc-eedings of the 2018 European Conference on Computer Vision, Munich, Sep 8-14, 2018. Berlin, Heidelberg: Springer, 2018: 404-419.
[15] Redmon J, Farhadi A. YOLOv3: an incremental improv-ment[J]. arXiv:1804.02767, 2018.
[16] Zhang S F, Wen L Y, Bian X, et al. Single-shot refinement neural network for object detection[C]//Proceedings of the 2018 IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, Jun 18-22, 2018. Piscataway: IEEE, 2018: 4203-4212.
[17] Lin T, Dollár P, Girshick R, et al. Feature pyramid networks for object detection[C]//Proceedings of the 2017 IEEE Con-ference on Computer Vision and Pattern Recognition, Honolulu, Jul 21-26, 2017. Piscataway: IEEE, 2017: 936-944.
[18] Zhou P, Ni B B, Geng C, et al. Scale-transferrable object detection[C]//Proceedings of the 2018 IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, Jun 18-22, 2018. Piscataway: IEEE, 2018: 528-537.
[19] Fu C Y, Liu W, Ranga A, et al. DSSD: deconvolutional single shot detector[J]. arXiv:1701.06659, 2017.
[20] Cui L S, Ma R, Lv P, et al. MDSSD: multi-scale deconv-olutional single shot detector for small objects[J]. arXiv: 1805.07009, 2018.
[21] Hu J, Shen L, Sun G. Squeeze-and-excitation networks[C]//Proceedings of the 2018 IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, Jun 18-22, 2018. Piscataway: IEEE, 2018: 7132-7141.
[22] Kong T, Sun F C, Hua W B, et al. Deep feature pyramid reconfiguration for object detection[C]//LNCS 11209: Proc-eedings of the 2018 European Conference on Computer Vision, Munich, Sep 8-14, 2018. Berlin, Heidelberg: Springer, 2018: 172-188.
[23] Wang X L, Girshick R, Gupta A, et al. Non-local neural networks[C]//Proceedings of the 2018 IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, Jun 18-22, 2018. Piscataway: IEEE, 2018: 7794-7803.